Optimal routing control of a construction machine by deep reinforcement learning

Zeyuan Sun, Masayuki Nakatani, Yutaka Uchimura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep reinforcement learning algorithms are rapidly growing, and expected to be applied to many industrial fields. In this paper, we proposed a method that combines a deep Q-network with batch normalization to generate an optimal route for a grading machine. The goal is to achieve autonomous operation of the grading machine. For the learning platform, a grading simulator was developed to emulate the grading work. The proposed method was evaluated with the grading simulator, and showed better route searching performance results than the conventional method.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages187-192
Number of pages6
ISBN (Electronic)9781538619469
DOIs
Publication statusPublished - 2018 Jun 1
Event15th IEEE International Workshop on Advanced Motion Control, AMC 2018 - Tokyo, Japan
Duration: 2018 Mar 92018 Mar 11

Other

Other15th IEEE International Workshop on Advanced Motion Control, AMC 2018
CountryJapan
CityTokyo
Period18/3/918/3/11

Fingerprint

Reinforcement learning
Simulators
Learning algorithms

Keywords

  • Artificial intelligence
  • Batch normalization
  • Deep reinforcement learning
  • Grading machine

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Mechanical Engineering
  • Control and Optimization

Cite this

Sun, Z., Nakatani, M., & Uchimura, Y. (2018). Optimal routing control of a construction machine by deep reinforcement learning. In Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018 (pp. 187-192). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AMC.2019.8371085

Optimal routing control of a construction machine by deep reinforcement learning. / Sun, Zeyuan; Nakatani, Masayuki; Uchimura, Yutaka.

Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 187-192.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sun, Z, Nakatani, M & Uchimura, Y 2018, Optimal routing control of a construction machine by deep reinforcement learning. in Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018. Institute of Electrical and Electronics Engineers Inc., pp. 187-192, 15th IEEE International Workshop on Advanced Motion Control, AMC 2018, Tokyo, Japan, 18/3/9. https://doi.org/10.1109/AMC.2019.8371085
Sun Z, Nakatani M, Uchimura Y. Optimal routing control of a construction machine by deep reinforcement learning. In Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 187-192 https://doi.org/10.1109/AMC.2019.8371085
Sun, Zeyuan ; Nakatani, Masayuki ; Uchimura, Yutaka. / Optimal routing control of a construction machine by deep reinforcement learning. Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 187-192
@inproceedings{ff12a10867d048b89316668b2561a14d,
title = "Optimal routing control of a construction machine by deep reinforcement learning",
abstract = "Deep reinforcement learning algorithms are rapidly growing, and expected to be applied to many industrial fields. In this paper, we proposed a method that combines a deep Q-network with batch normalization to generate an optimal route for a grading machine. The goal is to achieve autonomous operation of the grading machine. For the learning platform, a grading simulator was developed to emulate the grading work. The proposed method was evaluated with the grading simulator, and showed better route searching performance results than the conventional method.",
keywords = "Artificial intelligence, Batch normalization, Deep reinforcement learning, Grading machine",
author = "Zeyuan Sun and Masayuki Nakatani and Yutaka Uchimura",
year = "2018",
month = "6",
day = "1",
doi = "10.1109/AMC.2019.8371085",
language = "English",
pages = "187--192",
booktitle = "Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Optimal routing control of a construction machine by deep reinforcement learning

AU - Sun, Zeyuan

AU - Nakatani, Masayuki

AU - Uchimura, Yutaka

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Deep reinforcement learning algorithms are rapidly growing, and expected to be applied to many industrial fields. In this paper, we proposed a method that combines a deep Q-network with batch normalization to generate an optimal route for a grading machine. The goal is to achieve autonomous operation of the grading machine. For the learning platform, a grading simulator was developed to emulate the grading work. The proposed method was evaluated with the grading simulator, and showed better route searching performance results than the conventional method.

AB - Deep reinforcement learning algorithms are rapidly growing, and expected to be applied to many industrial fields. In this paper, we proposed a method that combines a deep Q-network with batch normalization to generate an optimal route for a grading machine. The goal is to achieve autonomous operation of the grading machine. For the learning platform, a grading simulator was developed to emulate the grading work. The proposed method was evaluated with the grading simulator, and showed better route searching performance results than the conventional method.

KW - Artificial intelligence

KW - Batch normalization

KW - Deep reinforcement learning

KW - Grading machine

UR - http://www.scopus.com/inward/record.url?scp=85048823289&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048823289&partnerID=8YFLogxK

U2 - 10.1109/AMC.2019.8371085

DO - 10.1109/AMC.2019.8371085

M3 - Conference contribution

SP - 187

EP - 192

BT - Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -